CSA-Trans: Code Structure Aware Transformer for AST

1 code implementation • 7 Apr 2024 • Saeyoon Oh, Shin Yoo

When applying the Transformer architecture to source code, designing a good self-attention mechanism is critical as it affects how node relationship is extracted from the Abstract Syntax Trees (ASTs) of the source code.

Code Summarization Stochastic Block Model +1

Equivariant Hypergraph Neural Networks

1 code implementation • 22 Aug 2022 • Jinwoo Kim, Saeyoon Oh, Sungjun Cho, Seunghoon Hong

Many problems in computer vision and machine learning can be cast as learning on hypergraphs that represent higher-order relations.

Transformers Generalize DeepSets and Can be Extended to Graphs and Hypergraphs

2 code implementations • NeurIPS 2021 • Jinwoo Kim, Saeyoon Oh, Seunghoon Hong

We present a generalization of Transformers to any-order permutation invariant data (sets, graphs, and hypergraphs).

2k Graph Regression +2

Transformers Generalize DeepSets and Can be Extended to Graphs & Hypergraphs

1 code implementation • NeurIPS 2021 • Jinwoo Kim, Saeyoon Oh, Seunghoon Hong

We present a generalization of Transformers to any-order permutation invariant data (sets, graphs, and hypergraphs).

2k Graph Regression